ClawHub
Back to skill

Security audit

Plusefin Analysis

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed financial-data integration that uses a PlusE API key and network requests for market research, with no evidence of hidden persistence, local data harvesting, destructive actions, or exfiltration beyond the expected API calls.

Install only if you are comfortable sending ticker symbols, market research requests, and related query context to PlusE using your PLUSEFIN_API_KEY. Avoid using it for confidential portfolio details or proprietary investment research unless you trust PlusE’s handling of that data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill requires environment access for an API key and instructs the agent to make external network requests, but it does not declare permissions accordingly. This weakens least-privilege controls and can cause users or hosting platforms to underestimate the skill's ability to exfiltrate prompts, tickers, or secrets to a third-party service.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The manifest advertises a general-purpose `calculate("2 + 2")` Python expression execution capability that is broader than the stated financial-data purpose. In agent contexts, expression evaluators often become a path to arbitrary code execution, sandbox escape attempts, data access, or abuse of host resources if inputs are not strictly constrained.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill tells the agent to use MCP, CLI, or curl against a third-party PlusE endpoint with a bearer API key, but it does not clearly warn that user requests and ticker queries are transmitted off-platform. This creates a privacy and trust problem: users may unknowingly disclose portfolio interests, research topics, or proprietary prompts to an external service.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill enables implicit invocation without any visible trigger constraints, so it may activate on broad finance-related queries without clear user intent. In a financial-analysis context, this can cause unintended access to external data sources or automated handling of sensitive investment-related requests, increasing the risk of overreach, surprise tool use, and prompt-routing abuse.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.